{"paper":{"title":"Time Domain Near Memory Computing Engine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A time-domain near-memory architecture performs low-precision MAC operations at 7.62 TOPS/W in a 4x4 prototype.","cross_cats":["cs.AR","cs.SY","eess.SY"],"primary_cat":"cs.ET","authors_text":"Sarthak Antal, Steve Enosh","submitted_at":"2026-05-13T22:31:07Z","abstract_excerpt":"The increasing computational demand of AI workloads has intensified the need for energy-efficient in-memory and near-memory computing architectures, particularly because data movement often consumes significantly more energy than computation itself. While fully digital architectures provide robust scalability and support higher-resolution computation, analog in-memory computing has demonstrated improved energy efficiency for low-precision workloads. However, its reliance on peripheral DACs and ADCs introduces additional power, area, and design overhead. To address these challenges, this work p"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The proposed time-domain near-memory computing architecture for low-precision MAC operations achieves 7.62 TOPS/W energy efficiency in a 4x4 prototype at 1 V supply and 40 MHz operating frequency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the N-pulse generator and counter-based accumulation maintain sufficient linearity and scalability when extended beyond the 4x4 prototype without significant power or area penalties.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A hybrid time-domain near-memory MAC prototype using pulse-encoded inputs and current-steering DAC weights achieves 7.62 TOPS/W energy efficiency with RTL-synthesized digital blocks for portability.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A time-domain near-memory architecture performs low-precision MAC operations at 7.62 TOPS/W in a 4x4 prototype.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cf87760833d8145484ae541b882597c4c852395c9d7235e41dd955358bafa5f2"},"source":{"id":"2605.14162","kind":"arxiv","version":1},"verdict":{"id":"a16fac64-05ba-4130-adb6-b8322d204c27","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:53:22.032236Z","strongest_claim":"The proposed time-domain near-memory computing architecture for low-precision MAC operations achieves 7.62 TOPS/W energy efficiency in a 4x4 prototype at 1 V supply and 40 MHz operating frequency.","one_line_summary":"A hybrid time-domain near-memory MAC prototype using pulse-encoded inputs and current-steering DAC weights achieves 7.62 TOPS/W energy efficiency with RTL-synthesized digital blocks for portability.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the N-pulse generator and counter-based accumulation maintain sufficient linearity and scalability when extended beyond the 4x4 prototype without significant power or area penalties.","pith_extraction_headline":"A time-domain near-memory architecture performs low-precision MAC operations at 7.62 TOPS/W in a 4x4 prototype."},"references":{"count":9,"sample":[{"doi":"10.1109/tvlsi.2020.3020286","year":2021,"title":"Murmann, ”Mixed-Signal Computing for Deep Neural Network Inference,” in IEEE Transactions on Very Large Scale Integra- tion (VLSI) Systems, vol","work_id":"d5eb27e6-3f16-4f59-859d-851bdc4f7e53","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/ojsscs.2021.3119910","year":2021,"title":"Jie, Micheal Flynn et al., ”An Overview of Noise-Shaping SAR ADC: From Fundamentals to the Frontier,” in IEEE Open Journal of the Solid-State Circuits Society, vol","work_id":"64dabc80-59aa-48c4-9519-553a80e6ea7d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/tcsii.2022.3169741","year":2022,"title":"Y . Zhang and Z. Zhu, ”Recent Advances and Trends in V oltage-Time Domain Hybrid ADCs,” in IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 69, no. 6, pp. 2575-2580, June 2022, doi: ","work_id":"d9edbac4-069e-4afd-8bb5-6638e8719bee","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"IEEE International Symposium on Circuits and Systems (ISCAS), 2025","work_id":"732531a3-9b8c-45bd-8463-597ba09989e2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"A 0.5-V Real-Time Computational CMOS Image Sensor With Programmable Kernel for Feature Extraction","work_id":"2ab6b4b2-63df-4789-96d7-5b187309b5e0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":9,"snapshot_sha256":"5a8cba0665c400f01bab9d53e4e4cadc3a6d5346ad6b320315dc3238ff45d4ec","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}